A Supervised Machine Learning Approach for Events Extraction out of Arabic Tweets

摘要

Tweets provide a continuous update on daily events, however they are noisy text, personalized and challenging to be understood by machines. This shows a need for event extraction and representation approaches. This research describes a state-of-the-art supervised machine learning approach for extracting events out of Arabic tweets. The proposed approach focuses on three research tasks: Task 1: Event Trigger Extraction, Task 2: Event Time Expression Extraction, Task 3: Event Type Identification. The proposed approach was evaluated on a dataset of 2k Arabic tweets and the evaluation results were promising. The approach performance was compared to an unsupervised rule-based approach from previous work using the same dataset. Results show that the proposed approach outperforms the unsupervised rule-based approach in tasks T1: event trigger extraction (F-1=92.6 vs. F-1=78.7) and T2: event time expression extraction (F-1=92.8 vs. F-1=88.35), whereas is acting relatively worse in T3: event type identification (Accuracy=80.1 vs. Accuracy=95.9).